Supercomputers/Systems/fortythree
Germany · operational · ai training
fortythree
Also known as hessian.AI 43; forty.THREE
Operated by hessian.AI at GSI Helmholtz Centre (Darmstadt) .
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
- 11.27 PFlop/s
- Rpeak
- 14.86 PFlop/s
- Rmax ÷ Rpeak
- 75.8%
- Cores
- 39,712
- Power
- 259.2 kW
- Per watt
- 43.5 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 | - 35 HPE Cray XD670 servers | Hewlett Packard Enterprise | 35 reported | Verified | hessian.aitop500.org |
| Accelerator | NVIDIA H100 SXM5 Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W 280 NVIDIA H100 GPUs, eight per server | NVIDIA | 280 reported | Verified | hessian.aitop500.org |
| CPU | - Xeon Platinum 8480+ 56C 2GHz | Intel | - | Reported | top500.org |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds Infiniband NDR | NVIDIA | - | Reported | top500.org |
The read
The first expansion stage of hessian.AI's fortytwo supercomputer, in the Green IT Cube at GSI in Darmstadt. hessian.AI's infrastructure page lists 280 NVIDIA H100 GPUs in 35 HPE Cray XD670 servers, each with dual Xeon Platinum processors and eight H100s; its 3 December 2024 announcement states 108th on the November 2024 TOP500, 42nd on the Green500 and direct water cooling. TOP500 lists Xeon Platinum 8480+ hosts, H100 SXM5 80GB on InfiniBand NDR, 39,712 cores, 11.27 PFlop/s Rmax, 14.86 PFlop/s Rpeak and 259.2 kW under Rocky Linux 8.9, then ranks of 130th, 152nd and 172nd to June 2026. It is a separate installation from fortytwo, the A100 system, which is its own row.
Timeline
- 2024 First operational source
- 2024-11 List debut at #42 (November 2024) source
- 2024-12-03 Announced 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
Change history
- 2026-10-02 Added fortythree, hessian.AI's H100 expansion
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 |
|---|---|---|
| hessian.ai | names system only | - |
| top500.org | does not name this system | NVIDIA H100 SXM5, NVIDIA InfiniBand NDR (Quantum-2) |
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.