COMPUTE ATLAS Supercomputer supply-chain graph
1153 systems 482 sites Sourced data

Supercomputers/Systems/UBELIX

Switzerland · operational · mixed

UBELIX

Also known as University of Bern Linux Cluster

Operated by University of Bern .

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
12,000
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
Accelerator -
NVIDIA GPU nodes with RTX 3090, RTX 4090, RTX 6000, A100, H100 and H200 cards, 160 GPUs in total
NVIDIA 160
reported
Reported hpc-unibe-ch.github.iohpc-unibe-ch.github.io
CPU -
AMD EPYC 9654, 24 nodes of 192 cores
AMD - Reported hpc-unibe-ch.github.io
CPU AMD EPYC 7742 (Rome)
CPUs
x86-64 · 64C · 2.25 GHz · 7 nm · 225 W
AMD EPYC 7742, 68 nodes of 128 cores
AMD - Reported hpc-unibe-ch.github.io

AI datacenter metrics

Figures beyond an accelerator count, each with who stated it. What can and cannot be compared across AI datacenters.

MetricValueAs ofBasisNoteSource
Accelerators 160 accelerators 2026-10 Operator stated Operator-stated GPU total across RTX, A100, H100 and H200 nodes. hpc-unibe-ch.github.io

The read

UBELIX is the University of Bern's HPC cluster. The hardware overview says it currently features about 12k CPU cores and 160 GPUs, with an InfiniBand interconnect. The CPU page lists about 250 nodes (24 nodes of 2x AMD EPYC 9654 with 192 cores, 68 nodes of 2x EPYC 7742 with 128 cores, and older nodes); the GPU page lists about 20 nodes with 8 GPUs each of RTX 3090, RTX 4090, RTX 6000, H100 and H200 types and a 6x A100 node. The 12,000 core figure is the operator's rounded 'about 12k'. Operator documentation only, so the tier is reported.

Timeline

No dated events recorded.

Change history

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 sourceResultFound on the page
hpc-unibe-ch.github.ionames system and partAMD EPYC 7742 (Rome)
hpc-unibe-ch.github.ionames system only-

Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.

Further reading