Supercomputers/Systems/FinisTerrae III
Spain · operational · mixed
FinisTerrae III
Also known as FT3; CESGA FinisTerrae III
Operated by CESGA at CESGA (Santiago de Compostela) .
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
- -
- Rpeak
- 4.36 PFlop/s
- Rmax ÷ Rpeak
- -
- Cores
- -
- 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 | - Atos supercomputer (contract awarded February 2021) | Atos | - | Reported | cesga.es |
| Accelerator | - NVIDIA A100 GPUs (docs: 141, infrastructure page: 128) | NVIDIA | - | Reported | cesga-docs.gitlab.iocesga.es |
| Accelerator | - 16 T4 nodes with one NVIDIA T4 GPU each | NVIDIA | 16 reported | Reported | cesga-docs.gitlab.iocesga.es |
| CPU | - Intel Xeon Ice Lake 8352Y 32C 2.2 GHz (CESGA docs: 714 processors; CESGA news: 708) | Intel | - | Reported | cesga-docs.gitlab.iocesga.es |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds InfiniBand HDR100 low-latency network | NVIDIA | - | Reported | cesga-docs.gitlab.iocesga.es |
The read
The Galician Supercomputing Centre's flagship system, an Atos cluster installed in 2021 (Atos announced it on 29 July 2021 as a 12-fold capacity increase) and in production from 2022, financed with about 7 million euros mostly from the European Regional Development Fund. The CESGA user guide lists 357 nodes on HDR InfiniBand with 714 Intel Xeon Ice Lake 8352Y (32 cores, 2.2 GHz) and 157 accelerators (141 A100 and 16 T4) at 4.36 PFlop/s, including 256 standard nodes, 64 nodes with two A100 each and two high-memory A100 nodes with five and eight GPUs. CESGA's infrastructure page and press material give slightly different totals (354 nodes, 22,656 cores, 128 A100 plus 16 T4, 4 PFlop/s, 118 TB memory, 5 PB Lustre), so no core count is recorded. Both sources are CESGA publications, so the tier is reported.
Site & facility
Change history
- 2026-10-04 Added FinisTerrae III, CESGA
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 |
|---|---|---|
| cesga-docs.gitlab.io | names system and part | NVIDIA InfiniBand HDR |
| cesga.es | names system and part | NVIDIA InfiniBand HDR |
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.