Supercomputers/Systems/Baskerville
United Kingdom · operational · mixed
Baskerville
Also known as Baskerville Tier 2
Operated by University of Birmingham at University of Birmingham (Baskerville) .
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
- 2.34 PFlop/s
- Rpeak
- 4.34 PFlop/s
- Rmax ÷ Rpeak
- 53.9%
- Cores
- 26,208
- 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 nodes (TOP500 lists SR670 V2), with OCF as technology partner | Lenovo | - | Reported | top500.orgblog.bham.ac.uk |
| Accelerator | NVIDIA A100 SXM4 40GB Accelerators CUDA (Ampere GA100) · 6,912C · 1.41 GHz · 7 nm · 400 W 184 NVIDIA A100 GPUs on HGX quad boards (46 nodes x 4) | NVIDIA | 184 reported | Reported | blog.bham.ac.uk |
| CPU | - Intel Xeon Platinum 8360Y 36C 2.4GHz (Ice Lake) | Intel | - | Reported | top500.org |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds Infiniband HDR | NVIDIA | - | Reported | top500.org |
| 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-to-node warm water cooling | Lenovo | - | Reported | blog.bham.ac.uk |
The read
EPSRC-funded Tier 2 accelerated computing facility at the University of Birmingham, built with the Rosalind Franklin Institute, the Alan Turing Institute and Diamond Light Source. Birmingham's launch post (14 September 2021) describes 184 NVIDIA A100 GPUs on NVIDIA HGX quad boards with Intel Ice Lake CPUs, Lenovo Neptune warm-water direct-to-node cooling, and 5 PB of disk plus 0.5 PB of flash; funding was agreed in October 2020 and pilot users started in June 2021. TOP500 lists it as a Lenovo ThinkSystem with Xeon Platinum 8360Y 36C and A100 over InfiniBand HDR, 26,208 cores, Rmax 2.34 PFlop/s and Rpeak 4.34 PFlop/s; it ranked 445th on the June 2024 list and 490th on the November 2024 list. Baskerville's current hardware page also lists a newer B200 partition, which is not counted here.
Timeline
- 2020-10 Announced source
- 2021-09 First operational source
- 2024-06 List debut at #445 (June 2024) source
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Site & facility
University of Birmingham (Baskerville)
- Location
- Birmingham, United Kingdom
- Cooling
- Direct liquid cooling, warm water
- Commissioned
- 2021
Change history
- 2026-10-02 Added Baskerville, Birmingham's A100 Tier 2 system, 445th on the June 2024 TOP500
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 |
|---|---|---|
| blog.bham.ac.uk | names system, part and count | NVIDIA A100 SXM4 40GB, Direct liquid cooling, warm water · counts: 184 |
| top500.org | names system and part | NVIDIA A100 SXM4 40GB, NVIDIA InfiniBand HDR |
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.