Supercomputers/Systems/Isambard-AI
United Kingdom · operational · ai training
Isambard-AI
Deep dive: Isambard-AI versus Alps: two GH200 routes
Operated by University of Bristol at National Composites Centre, Bristol .
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: 1263 of 1345 systems have a readable citation that names them, and 56 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
- 7.42 PFlop/s
- Rpeak
- 9.29 PFlop/s
- Rmax ÷ Rpeak
- 79.9%
- Cores
- 34,272
- Power
- 117.08 kW
- Per watt
- 63.4 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 | - HPE Cray EX4000 | Hewlett Packard Enterprise | - | Reported | docs.isambard.ac.ukhpe.com |
| Accelerator | NVIDIA GH200 Grace Hopper Superchip Accelerators Arm CPU + CUDA GPU · TSMC 4N NVIDIA GH200 Superchip | NVIDIA | - | Reported | docs.isambard.ac.ukhpe.com |
| CPU | NVIDIA Grace CPUs Armv9 (Neoverse V2) · 72C · 3.1 GHz · TSMC 4N NVIDIA GH200 Superchip | NVIDIA | - | Reported | docs.isambard.ac.ukhpe.com |
| Interconnect | HPE Slingshot-11 Interconnect Dragonfly · 200 Gb/s per port · Around 2 microseconds Slingshot-11 | Hewlett Packard Enterprise | - | Reported | docs.isambard.ac.ukhpe.com |
| Storage | HPE Cray ClusterStor E1000 Storage Lustre appliance, flash and disk tiers · 700 PB on Frontier (Orion) · About 10 TB/s peak 20 PiByte Cray ClusterStor | Hewlett Packard Enterprise | - | Reported | bristol.ac.uk |
| Storage | VAST Data Platform Storage Disaggregated shared-everything 3.5 PiByte VAST solutions | VAST Data | - | Reported | bristol.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 HPE Cray EX cabinet: 100% direct liquid cooled | Hewlett Packard Enterprise | - | Reported | docs.isambard.ac.ukhpe.com |
| Operating system | HPE Cray Operating System Operating systems SUSE-derived Linux, container-based management · Proprietary layer over open-source Linux HPE Cray Operating System | Hewlett Packard Enterprise | - | Reported | docs.isambard.ac.ukhpe.com |
AI datacenter metrics
Figures beyond an accelerator count, each with who stated it. What can and cannot be compared across AI datacenters.
| Metric | Value | As of | Basis | Note | Source |
|---|---|---|---|---|---|
| Accelerators | 168 accelerators | 2026-10 | Operator stated | Phase 1 only: 42 nodes x 4 GH200 superchips. Phase 2 (5,280) is its own system row. | docs.isambard.ac.uk |
The read
The UK's national AI research resource, built on HPE Cray EX4000 with NVIDIA Grace Hopper, and notable for how fast it was delivered relative to the national-laboratory procurements elsewhere in this dataset. This row is phase 1 of a two-phase build: a second, roughly 29x larger HPL submission on the same site carries its own row, isambard-ai-phase2, rather than being folded into this one, because TOP500 itself treats them as two separate system entries.
Timeline
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Site & facility
National Composites Centre, Bristol
- Location
- Bristol, United Kingdom
- Cooling
- Direct liquid cooling
- Commissioned
- 2024
Change history
- 2026-10-04 Added AI datacenter metrics for isambard-ai
- 2026-09-22 Gained a Green500 rank pointer (#2 on the 2024-06 list)
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 |
|---|---|---|
| top500.org | names system and part | NVIDIA GH200 Grace Hopper Superchip, NVIDIA Grace, HPE Slingshot-11, HPE Cray Operating System, HPE Cray ClusterStor E1000 |
| bristol.ac.uk | names system and part | NVIDIA GH200 Grace Hopper Superchip, Direct liquid cooling, warm water, NVIDIA Grace, HPE Cray Operating System, HPE Cray ClusterStor E1000, VAST Data Platform |
Checked 2026-10-13 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Inside a node
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
Power and cooling
Why air ran out at 20 kW a rack, how warm-water cooling removes the chillers, and what PUE conceals.
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.