Supercomputers/Systems/JURECA
Germany · decommissioned · hpc
JURECA
Also known as JURECA Cluster Module (2015)
Operated by Forschungszentrum Julich at Julich Supercomputing Centre .
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
- 1.42 PFlop/s
- Rpeak
- 1.69 PFlop/s
- Rmax ÷ Rpeak
- 84.0%
- Cores
- -
- Power
- 828.55 kW
- Per watt
- 1.7 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 | - T-Platforms V-Class blades | T-Platforms | - | Reported | top500.orgapps.fz-juelich.de |
| Accelerator | - NVIDIA K80 GPUs in 75 nodes (two per node) | NVIDIA | - | Reported | apps.fz-juelich.de |
| CPU | - Two Intel Xeon E5-2680 v3 Haswell 12-core 2.5 GHz CPUs per node | Intel | - | Reported | apps.fz-juelich.de |
| Interconnect | - Mellanox EDR InfiniBand, non-blocking fat tree | Mellanox NVDANASDAQ
rolls up to NVIDIA | - | Reported | apps.fz-juelich.de |
The read
The original 2015 cluster module of Julich's JURECA, built by T-Platforms from V-Class blades: 1,872 nodes of two Xeon E5-2680 v3 12-core CPUs each, 75 of them with two NVIDIA K80 GPUs, on Mellanox EDR InfiniBand, with a 1.8 petaflop CPU peak plus 0.44 petaflop from the GPUs per JSC. TOP500 lists this configuration at 1.42 petaflops Rmax and 1.69 petaflops Rpeak, 50th on the November 2015 list; the later TOP500 entries include the 2017 Booster module and are not recorded here. JSC says the cluster module was retired in 2020 and replaced by JURECA-DC. JSC counts 45,216 CPU cores against TOP500's 49,476, and its peak differs from TOP500's, so no core count is recorded. TOP500 is the only source for Rmax, so the tier is reported.
Timeline
- 2015 First operational source
- 2015-11 List debut at #50 (November 2015) source
- 2020 Decommissioned 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
Julich Supercomputing Centre
- Location
- Julich, Germany
- Cooling
- Direct liquid cooling
- Commissioned
- 2004
Change history
- 2026-10-02 Added the original JURECA cluster module at Julich
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 |
|---|---|---|
| apps.fz-juelich.de | names system only | - |
| top500.org | names system only | - |
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.