Supercomputers/Systems/Devana
Slovakia · operational · hpc
Devana
Operated by Computing Centre SAV at SAV Computing Centre (Bratislava) .
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
- 800.00 TFlop/s
- Rmax ÷ Rpeak
- -
- Cores
- 9,472
- Power
- 130 kW
- 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 SD630 V2 (CPU nodes) and SR670 V2 (GPU nodes) | Lenovo | - | Verified | vs.sav.skixperta.com |
| Accelerator | - 4x NVIDIA A100 40GB GPGPU accelerators per GPU node, 8 GPU nodes | NVIDIA | - | Verified | vs.sav.skixperta.com |
| CPU | - Intel Xeon Gold 6338 (Ice Lake-SP) 32C 2.0GHz 205W, 140 CPU nodes at 64 cores/node | Intel | 140 reported | Verified | vs.sav.skixperta.com |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds HDR InfiniBand, non-blocking fat-tree topology (Ixperta states 100 Gb/s, sub-10 microsecond latency) | NVIDIA | - | Reported | vs.sav.skixperta.com |
| Operating system | CentOS Operating systems Linux distribution, RHEL-compatible rebuild · Open source, community-maintained CentOS 7.x on x86_64 | The CentOS Project | - | Reported | vs.sav.sk |
The read
Slovakia's national supercomputer, replacing the older Aurela system, operated by the Computing Centre of the Slovak Academy of Sciences (SAV) in Bratislava under Slovakia's National Supercomputing Centre / EuroCC programme. SAV's own service page and Lenovo's integration partner Ixperta independently agree on the architecture: Lenovo hardware with 140 CPU nodes (2x Intel Xeon Gold 6338 Ice Lake, 32C/2.0GHz/205W, 64 cores per node) and 8 GPU nodes (4x NVIDIA A100 40GB GPGPU accelerators each), for up to 800 TFlop/s theoretical peak performance and roughly 130 kW power draw. The two sources differ on how precisely to describe the fabric (SAV states HDR InfiniBand in a non-blocking fat-tree; Ixperta states 100 Gb/s InfiniBand with sub-10-microsecond latency), so that edge stays reported. SAV's page states the node operating system as CentOS 7.x. Installation began November 2022 and Ixperta states deployment and testing took about five months, so first_operational_date is recorded as 2023 without a specific month. No TOP500 submission was found for Devana, so ranked is 0 and rmax_pflops is left blank with rpeak_pflops recorded as the stated theoretical peak.
Timeline
- 2023 First operational source
Site & facility
SAV Computing Centre (Bratislava)
- Location
- Bratislava, Slovakia
- Commissioned
- 2022
Change history
- 2026-09-24 Devana added (Slovakia)
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 |
|---|---|---|
| vs.sav.sk | names system and part | NVIDIA InfiniBand HDR, CentOS |
| ixperta.com | blocked our fetch | - |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Further reading
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.
Programming a supercomputer
The software stack beneath the application, and why the OS is now a sovereignty signal as much as a technical choice.