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

Supercomputers/Systems/Oxford ARC

United Kingdom · operational · mixed

Oxford ARC

Also known as ARC and HTC clusters; University of Oxford Advanced Research Computing

Operated by University of Oxford .

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
23,328
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 P100, V100, A100, RTX, H100 and L40S GPUs on 51 htc GPU nodes
NVIDIA - Reported arc-user-guide.readthedocs.io
CPU -
Intel Xeon Platinum Cascade Lake 48-core nodes, 262 nodes on the arc cluster
Intel - Reported arc-user-guide.readthedocs.io
CPU AMD EPYC 9005 (Turin)
CPUs
x86-64 · 192C · 2.7 GHz · TSMC N3E · 500 W
AMD EPYC 9825 Turin 288-core nodes, 10 nodes on the arc cluster
AMD - Reported arc-user-guide.readthedocs.io
Interconnect NVIDIA InfiniBand HDR
Interconnect
Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds
Mellanox HDR100 InfiniBand on the arc cluster
NVIDIA - Reported arc-user-guide.readthedocs.io

The read

ARC is the University of Oxford's Advanced Research Computing service, built around two Slurm clusters. The ARC capability cluster has 262 48-core Cascade Lake nodes (HDR100 InfiniBand) and 10 288-core AMD EPYC 9825 Turin nodes (NDR 400 InfiniBand), stated as 15,456 CPU cores. The HTC throughput cluster has 124 nodes and 7,872 cores, 51 of them GPU nodes with P100, V100, A100, RTX, H100 and L40S cards. The 23,328 core figure is our sum of the two stated totals. Some nodes are co-investment hardware with restricted use. 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
arc-user-guide.readthedocs.ionames system and partAMD EPYC 9005 (Turin), NVIDIA InfiniBand HDR

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

Further reading