Supercomputers/Systems/Clementina XXI
Argentina · operational · mixed
Clementina XXI
Operated by SMN Argentina .
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
- 5.39 PFlop/s
- Rpeak
- 12.58 PFlop/s
- Rmax ÷ Rpeak
- 42.8%
- Cores
- 43,008
- 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 | - Lenovo ThinkSystem SD650-I V3, 80 nodes | Lenovo | 80 reported | Verified | top500.orgargentina.gob.ar |
| Accelerator | Intel Data Center GPU Max 1550 Accelerators oneAPI (Xe-HPC) · Intel 7 / TSMC N5 · 600 W Intel Data Center GPU Max 1550, 4 per GPU node on 74 nodes | Intel | 296 estimated | Verified | top500.orgdocs.clementinaxxi.org.ar |
| CPU | - Intel Xeon CPU Max 9462 32C 2.7GHz, two sockets per node on 80 nodes | Intel | 160 estimated | Verified | top500.orgdocs.clementinaxxi.org.ar |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds Infiniband NDR | NVIDIA | - | Reported | top500.org |
| Operating system | Red Hat Enterprise Linux Operating systems Linux distribution · Open source, commercial support subscription Red Hat Enterprise Linux | Red Hat | - | Reported | top500.org |
The read
Argentina's flagship national supercomputer, a Lenovo ThinkSystem SD650-I V3 machine in the national weather service's data center in Buenos Aires, shared across the national science system under a governance commission. Its documentation lists 80 nodes: 74 GPU nodes with four Intel Data Center GPU Max 1550 each and six CPU-only nodes, all with dual Xeon CPU Max 9462 and 512 GB of RAM plus HBM, on NDR InfiniBand. The acquisition was reported at 1,740 million pesos, and its best TOP500 position was 199th on the November 2024 list (289th by June 2026). The CPU and Intel GPU edges are verified by TOP500 and the operator's documentation. TOP500's 43,008 core count includes GPU cores. The exact site coordinates were not found in a page we fetched, so the system is left unlocated, and no go-live date was found. Rmax and Rpeak come from TOP500 alone, so the system tier is reported.
Timeline
- 2024-11 List debut at #199 (November 2024) source
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Change history
- 2026-10-01 Added Clementina XXI (SMN Argentina)
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 |
|---|---|---|
| docs.clementinaxxi.org.ar | names system only | - |
| top500.org | 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.