Supercomputers/Systems/Roihu
Finland · operational · mixed
Roihu
Operated by CSC at LUMI Data Center, Kajaani .
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
- -
- 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 | - BullSequana XH3000 hybrid system, liquid-cooled | Bull | - | Reported | csc.fibull.com |
| Accelerator | NVIDIA GH200 Grace Hopper Superchip Accelerators Arm CPU + CUDA GPU · TSMC 4N 132 GPU nodes with four NVIDIA GH200 superchips each | NVIDIA | 528 reported | Reported | csc.fi |
| CPU | AMD EPYC 9005 (Turin) CPUs x86-64 · 192C · 2.7 GHz · TSMC N3E · 500 W 486 CPU nodes, two 192-core AMD EPYC Turin 9965 each | AMD | - | Reported | csc.fi |
The read
Finland's new national supercomputer, a liquid-cooled Bull BullSequana XH3000 hybrid system in CSC's Kajaani data centre alongside LUMI, replacing Puhti and Mahti. CSC lists 486 CPU nodes with two 192-core AMD EPYC Turin 9965 CPUs each and 132 GPU nodes with four NVIDIA GH200 superchips each, a 6.0 PiB flash scratch file system and a 0.5 PiB project and home system. Pilot use began in April 2026, the system was inaugurated in May 2026 and became generally available on 29 June 2026. CSC states only estimated HPL of above 10 PFlop/s for the CPU nodes and above 20 PFlop/s for the GPU nodes, and different CSC and press pages quote different combined theoretical peaks (33.9 and 49 PFlop/s), so no FLOPS figure is recorded. Bull's own press release confirms the delivery, the Kajaani location and the liquid-cooled BullSequana platform but not the node counts; it has no TOP500 entry that was confirmed.
Timeline
- 2026-06 First operational source
Site & facility
LUMI Data Center, Kajaani
- Location
- Kajaani, Finland
- Cooling
- Direct liquid cooling with waste-heat recovery
- PUE
- 1.03
- Commissioned
- 2022
Change history
- 2026-10-01 Added Roihu (CSC)
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 |
|---|---|---|
| csc.fi | names system and part | NVIDIA GH200 Grace Hopper Superchip |
| bull.com | names system only | - |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.