Supercomputers/Systems/Quinde I
Ecuador · decommissioned · hpc
Quinde I
Also known as Supercomputador Quinde I
Operated by Empresa Publica Yachay EP at Ciudad del Conocimiento Yachay Data Center .
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
- 232.00 TFlop/s
- Rpeak
- -
- Rmax ÷ Rpeak
- -
- Cores
- 1,640
- 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 | - IBM-built MIMD NUMA cluster of 88 nodes (84 compute + 4 administration) in a modular container data center | IBM | - | Reported | eluniverso.comelcomercio.com |
| Accelerator | - Roughly 4,992 CUDA cores across the GPU partition per Spanish Wikipedia; exact GPU model/vendor not stated in any source found, NVIDIA inferred from 'CUDA cores' terminology | NVIDIA | - | Reported | es.wikipedia.org |
| CPU | - x86-64 host CPUs, two sockets per node, 1,640 cores total | IBM | 1,640 reported | Reported | es.wikipedia.org |
| Interconnect | Mellanox InfiniBand EDR Interconnect Fat tree · 100 Gb/s per 4x port · About 0.9 microseconds Mellanox InfiniBand EDR at 100 Gb/s (Mellanox was independent at build time, predating NVIDIA's 2020 acquisition) | Mellanox NVDANASDAQ
rolls up to NVIDIA | - | Reported | es.wikipedia.org |
The read
Ecuador's first supercomputer and, at debut, the second-largest in Latin America after Brazil's Santos Dumont. An IBM-built MIMD NUMA cluster of 88 nodes (84 compute, 4 administration; x86-64, two sockets per node, 1,640 CPU cores and roughly 4,992 CUDA cores per Spanish Wikipedia) installed in a modular shipping-container data center at the 'Ciudad del Conocimiento Yachay' in San Miguel de Urcuqui, acquired in October 2016 and entering service on 12-14 December 2017 under the public enterprise Yachay EP, for use mainly by Yachay Tech University. El Universo and El Comercio (independent Ecuadorian outlets) agree on the operator, the container-based design and the timeline; El Comercio reports a USD 6.2 million cost (partly financed via an Ecuador-Spain debt-swap programme) while a later Teleamazonas retrospective cites USD 16 million, a discrepancy this dataset does not resolve. Rmax of 232 TFlop/s and cores are taken from Spanish Wikipedia's technical summary, which is the only source found with those specific figures, so rpeak is left blank given inconsistent figures across secondary sources (352 vs 489 TFlop/s reported in different places) rather than guessed. Teleamazonas (10 January 2023) reports the machine had been 'practically abandoned' and non-operational for over four years, with a Ministry official in November 2020 estimating at least USD 1 million would be needed to restore it, funding that was never allocated; status is therefore recorded as decommissioned as of that report, with no precise decommissioning date found. No TOP500 submission was confirmed despite Wikipedia listing a generic '>500' ranking note, so ranked is left at 0.
Site & facility
Ciudad del Conocimiento Yachay Data Center
- Location
- San Miguel de Urcuqui, Ecuador
- Commissioned
- 2017
Change history
- 2026-09-27 Added Quinde I (Yachay Tech, Ecuador)
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 |
|---|---|---|
| elcomercio.com | names system only | - |
| eluniverso.com | names system only | - |
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.