Supercomputers/Systems/SuperMUC Phase 2
Germany · decommissioned · hpc
SuperMUC Phase 2
Operated by LRZ at Leibniz Supercomputing Centre, Garching .
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
- 2.81 PFlop/s
- Rpeak
- 3.58 PFlop/s
- Rmax ÷ Rpeak
- 78.5%
- Cores
- 86,016
- Power
- 1.48 MW
- Per watt
- 1.9 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 NeXtScale nx360 M5, 3,072 nodes across six islands | Lenovo | - | Verified | top500.orgdoku.lrz.de |
| CPU | Intel Xeon E5-2697 v3 CPUs x86-64 · 14C · 2.6 GHz · 22 nm · 145 W Xeon E5-2697 v3 14C 2.62GHz, two per node | Intel | - | Verified | top500.orgdoku.lrz.de |
| Interconnect | Mellanox InfiniBand FDR Interconnect Fat tree · 56 Gb/s per 4x port · About 1 microsecond InfiniBand FDR14, pruned 4:1 tree between islands | NVIDIA | - | Verified | top500.orgdoku.lrz.de |
| Storage | IBM Spectrum Scale ESS (GPFS) Storage Parallel filesystem (GPFS), erasure-coded declustered RAID · 250 PB on Summit (Alpine) · About 2.5 TB/s IBM GPFS, shared with SuperMUC Phase 1 | IBM | - | Reported | doku.lrz.de |
| Cooling | Direct liquid cooling, warm water Cooling Direct-to-chip cold plates, facility water loop · Removes 90+ percent of node heat to liquid High Temperature Liquid Cooling, shared design with SuperMUC Phase 1 | Lenovo | - | Reported | doku.lrz.de |
The read
The Haswell-generation extension to SuperMUC, 3,072 Lenovo NeXtScale nx360 M5 nodes across six network islands, 21st on the June 2015 TOP500. LRZ's own page and TOP500 independently name the NeXtScale hardware and the Xeon E5-2697 v3 processor, so those edges are verified; Rmax, Rpeak and core count are TOP500's alone. It shared SuperMUC's GPFS storage and warm-water cooling and retired alongside it at the end of 2019, ahead of SuperMUC-NG. Recorded as its own row because TOP500 lists it as a distinct system entry from Phase 1, the same split this dataset already applies to Snellius and MareNostrum 5. TOP500 is the only source for Rmax, Rpeak and core count, so the tier is reported.
Timeline
- 2015-06 List debut at #21 (June 2015) source
- 2015-06 First operational source
- 2019-12 Decommissioned at year end, fully superseded by SuperMUC-NG source
- 2019-12 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
Leibniz Supercomputing Centre, Garching
- Location
- Garching, Germany
- Cooling
- Direct warm-water cooling
- Commissioned
- 2006
Change history
- 2026-09-23 Added as its own row, matching how TOP500 lists it separately from SuperMUC Phase 1
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 |
|---|---|---|
| doku.lrz.de | blocked our fetch | - |
| top500.org | names system and part | Intel Xeon E5-2697 v3, Mellanox InfiniBand FDR |
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.