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

Supercomputers/Systems/Mary Coombs

United Kingdom · operational · mixed

Mary Coombs

Also known as STFC Hartree Centre Mary Coombs

Operated by STFC Hartree Centre at Hartree Centre Supercomputing Centre (Daresbury) .

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
-
operator stated
Rpeak
24.41 PFlop/s
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 -
Lenovo ThinkSystem Neptune, 157 compute nodes
Lenovo - Reported hartree.stfc.ac.uknews.lenovo.com
Accelerator -
NVIDIA H100 GPUs on 157 compute nodes
NVIDIA - Reported hartree.stfc.ac.uk
Cooling Direct liquid cooling, warm water
Cooling
Direct-to-chip cold plates, facility water loop · Removes 90+ percent of node heat to liquid
Lenovo Neptune direct warm-water liquid cooling in a closed loop
Lenovo - Reported hartree.stfc.ac.uknews.lenovo.com

The read

The STFC Hartree Centre's GPU supercomputer, named for Mary Coombs, the UK's first female commercial programmer, a Lenovo ThinkSystem Neptune system of 157 compute nodes with NVIDIA H100 GPUs and warm-water direct liquid cooling, housed in the new GBP30 million Supercomputing Centre at Daresbury Laboratory. The Hartree Centre describes it as a 24.41 PFlop/s system ten times faster than its predecessor Scafell Pike while using 75 percent less energy, and UKRI announced its launch on 20 October 2025, which is the start date used here. Lenovo and trade press announced the order in March 2024 at 44.7 PFlop/s, a larger figure than the 24.41 PFlop/s the centre now quotes; this row uses the centre's current figure and does not know which precision the 24.41 refers to. GPUs per node, the CPU model, the interconnect and the storage are not stated in any fetched source, so those are left out. The machine is part of the GBP210 million Hartree National Centre for Digital Innovation programme with IBM and serves industry and public-sector users. Only the operator and its parent body state the performance and node count, so the tier is reported.

Timeline

Site & facility

Hartree Centre Supercomputing Centre (Daresbury)

Location
Daresbury, Cheshire, United Kingdom
Cooling
Direct liquid cooling (warm water)
Commissioned
2025

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
hartree.stfc.ac.uknames system only-
ukri.orgnames system and partDirect liquid cooling, warm water

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

Further reading