Supercomputers/Systems/PERUN
Slovakia · operational · mixed
PERUN
Also known as TUKE PERUN supercomputer
Operated by Technical University of Kosice at TUKE Supercomputing Center (Kosice) .
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
- 10.21 PFlop/s
- Rpeak
- 11.43 PFlop/s
- Rmax ÷ Rpeak
- 89.3%
- Cores
- 30,784
- Power
- 199.85 kW
- Per watt
- 51.1 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 ProLiant Compute XD685 (AI partition), HPE Cray XD2000 (universal partition) | Hewlett Packard Enterprise | - | Verified | top500.orghpc.tuke.sk |
| Accelerator | NVIDIA H200 SXM Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W NVIDIA H200 SXM5 141 GB, eight per node on 26 AI nodes (arithmetic from node count) | NVIDIA | 208 estimated | Verified | top500.orghpc.tuke.sk |
| CPU | AMD EPYC 9005 (Turin) CPUs x86-64 · 192C · 2.7 GHz · TSMC N3E · 500 W AMD EPYC 9535 64C 2.4GHz, two per node on 26 AI nodes | AMD | - | Verified | top500.orghpc.tuke.sk |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds Infiniband NDR400 (4 x 400 Gb/s per GPU node) | NVIDIA | - | Verified | top500.orghpc.tuke.sk |
The read
Slovakia's new national-class supercomputer at the Technical University of Kosice, launched on 20 November 2025 with support from the Slovak Recovery and Resilience Plan. TOP500 lists an HPE ProLiant Compute XD685 system with AMD EPYC 9535 64-core 2.4 GHz CPUs, NVIDIA H200 SXM5 141 GB GPUs and InfiniBand NDR400 under Rocky Linux 9.5: 30,784 cores, Rmax 10.21 PFlop/s, Rpeak 11.43 PFlop/s and 199.85 kW (160.54 kW optimized). The TUKE architecture page describes a Universal partition of 32 HPE Cray XD2000 nodes with dual EPYC 9745 and an AI partition of 26 HPE ProLiant XD685 nodes with dual EPYC 9535 and eight H200 GPUs each, with 4 x 400 Gb/s NDR InfiniBand per GPU node; TUKE quotes 10.7 PFlops Rmax versus the 10.21 measured on TOP500, and the TOP500 value is recorded. It ranked 162nd on the November 2025 list and 182nd on June 2026. TOP500 also carries a separate PERUN entry attributed to the Slovak Academy of Sciences (Eviden, rank 125 in November 2025) which is not covered here.
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
Change history
- 2026-10-02 Added PERUN, Technical University of Kosice's H200 supercomputer
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 |
|---|---|---|
| hpc.tuke.sk | names system and part | AMD EPYC 9005 (Turin), NVIDIA H200 SXM, NVIDIA InfiniBand NDR (Quantum-2) |
| top500.org | names system and part | AMD EPYC 9005 (Turin), NVIDIA H200 SXM, 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.