Germany · decommissioned · hpc

COBRA

Also known as MPCDF COBRA; MPI/IPP COBRA

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: 5.61 PFlop/s
Rpeak: 9.79 PFlop/s
Rmax ÷ Rpeak: 57.3%
Cores: 127,520
Power: 1.64 MW
Per watt: 3.4 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	- Intel Compute Module HNS2600BP cluster	Intel INTCNASDAQ	-	Reported	top500.org docs.mpcdf.mpg.de
Accelerator	NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W 128 NVIDIA Tesla V100 32GB GPUs added December 2018	NVIDIA NVDANASDAQ	128 reported	Reported	docs.mpcdf.mpg.de
CPU	Intel Xeon Gold 6148 CPUs x86-64 · 20C · 2.4 GHz · 14 nm · 150 W Two Intel Xeon Gold 6148 20C 2.4GHz per node	Intel INTCNASDAQ	-	Verified	top500.org docs.mpcdf.mpg.de
Interconnect	Omni-Path Architecture Interconnect Fat tree · 100 Gb/s per port · About 1 microsecond 100 Gb/s Omni-Path, fat tree within islands of about 636 nodes	Intel INTCNASDAQ	-	Verified	top500.org docs.mpcdf.mpg.de

The read

The Max Planck Computing and Data Facility flagship of 2018: an Intel-built cluster of dual Xeon Gold 6148 (20-core) nodes on 100 Gb/s Omni-Path in non-blocking islands of about 636 nodes, later extended with 64 Tesla V100 and 120 Quadro RTX 5000 GPU nodes. TOP500 lists 127,520 cores with Rmax 5.61 and Rpeak 9.79 PFlop/s at 1,635 kW; MPCDF quotes 11.4 PFlop/s double-precision peak for the whole machine including GPUs. MPCDF documents batch processing ending on 1 July 2024 and login nodes retired on 19 July 2024. It ranked 36th on the November 2019 TOP500.

Timeline

2018 First operational source
2019-11 List debut at #36 (November 2019) source
2024-07 Decommissioned source

Public list appearances

Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.

#36: TOP500, November 2019 →

Site & facility

MPCDF Garching

Location: Garching, Germany
Commissioned: 2021

mpcdf.mpg.de top500.org

Change history

2026-10-02 Added COBRA, the Max Planck Computing and Data Facility Skylake cluster, 36th on the November 2019 TOP500

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
docs.mpcdf.mpg.de	names system, part and count	Intel Xeon Gold 6148, NVIDIA Tesla V100 · counts: 128
top500.org	names system and part	Intel Xeon Gold 6148, Omni-Path Architecture

Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.