Supercomputers/Systems/Noctua 2
Germany · operational · hpc
Noctua 2
Operated by Paderborn PC2 .
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
- 4.19 PFlop/s
- Rpeak
- 5.30 PFlop/s
- Rmax ÷ Rpeak
- 79.1%
- Cores
- 135,168
- Power
- 868.74 kW
- Per watt
- 4.8 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 | - Atos BullSequana XH2000 | Atos | - | Verified | pc2.uni-paderborn.detop500.org |
| Accelerator | - 32 GPU nodes with four NVIDIA A100 plus one DGX A100 node with eight (136 A100 as stated by PC2) | NVIDIA | 136 reported | Reported | pc2.uni-paderborn.de |
| Accelerator | - 48 Xilinx Alveo U280 FPGA cards in FPGA nodes | AMD | 48 reported | Reported | pc2.uni-paderborn.de |
| Accelerator | - 32 Intel Stratix 10 FPGA cards in FPGA nodes | Intel | 32 reported | Reported | pc2.uni-paderborn.de |
| CPU | AMD EPYC 7763 (Milan) CPUs x86-64 · 64C · 2.45 GHz · 7 nm · 280 W Dual AMD EPYC 7763 Milan per CPU node (TOP500: 135,168 CPU cores; PC2: 143,872 cores in total) | AMD | - | Verified | pc2.uni-paderborn.detop500.org |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds Mellanox InfiniBand HDR/HDR100 network | NVIDIA | - | Verified | pc2.uni-paderborn.detop500.org |
The read
Paderborn University's NHR supercomputer, an Atos BullSequana XH2000 system inaugurated in 2022. PC2 lists 990 standard, 66 large-memory and 5 huge-memory nodes with dual AMD EPYC 7763 Milan CPUs (143,872 cores in total), 32 GPU nodes with four NVIDIA A100 plus one DGX A100 node (136 A100), and 36 FPGA nodes with 48 Xilinx Alveo U280 and 32 Intel Stratix 10 cards, on Mellanox InfiniBand HDR with a 6 PB Lustre file system; peak is 5.4 PFlop/s for the CPUs and 2.49 PFlop/s for GPU tensor cores. TOP500 lists 135,168 cores, 4.19 PFlop/s Rmax, 5.30 PFlop/s Rpeak and 868.74 kW, ranked 121st in June 2022, matching PC2's own ranking statement. The core count here is TOP500's CPU-partition figure.
Timeline
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Change history
- 2026-10-02 Added Noctua 2 (Paderborn PC2)
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 |
|---|---|---|
| pc2.uni-paderborn.de | names system and part | AMD EPYC 7763 (Milan), NVIDIA InfiniBand HDR |
| top500.org | names system and part | AMD EPYC 7763 (Milan), 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.